This skill reviews library code to provide feedback on API naming, type safety, error handling, and consistency with industry standards.

Install

mkdir -p .claude/skills/dx-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/7177" && unzip -o skill.zip -d .claude/skills/dx-review && rm skill.zip

Installs to .claude/skills/dx-review

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Review developer experience and API ergonomics
46 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Evaluate API discoverability and consistency
  • Assess ergonomics and developer friction
  • Review error message clarity
  • Check TypeScript definition precision
  • Audit JSDoc documentation

How it works

It guides the reviewer through a structured evaluation of the API surface, types, and documentation to identify usability issues.

Inputs & outputs

You give it
Library public API surface
You get back
DX review report with recommendations

When to use dx-review

  • Auditing API surface for usability
  • Reviewing JSDoc and documentation
  • Improving error message clarity
  • Evaluating type safety of public APIs

About this skill

You are reviewing the developer experience (DX) of the library to ensure it feels good to use. As a library consumed by other developers, ergonomics matter as much as functionality.

Your Task

  1. Identify scope - Based on the conversation context, determine what module or feature to review. If no specific scope is mentioned, review the main public API.
  2. Analyze the API surface - How do developers interact with this code?
  3. Evaluate ergonomics - Is it intuitive, consistent, and pleasant to use?
  4. Report findings - Document issues and recommendations

DX Evaluation Criteria

1. Discoverability

  • Can developers find what they need?
  • Are method names intuitive and searchable?
  • Is the API surface appropriately sized (not too sprawling)?

2. Consistency

  • Do similar operations work the same way?
  • Are naming conventions consistent across the API?
  • Do return types follow predictable patterns?

3. Ergonomics

  • Is the common case easy? (pit of success)
  • Are required parameters actually required?
  • Do defaults make sense for typical usage?
  • Is there unnecessary boilerplate?

4. Error Experience

  • Are errors actionable? (tells you what went wrong AND how to fix it)
  • Do errors surface at the right time? (fail fast)
  • Are error types specific enough to catch programmatically?

5. Type Experience

  • Does autocomplete guide developers?
  • Are types precise (not too wide like any or string)?
  • Do generics add value or just complexity?

6. Documentation in Code

  • Are public methods documented with JSDoc?
  • Do examples in comments actually work?
  • Are parameter constraints documented?

7. Comparison to Standards

  • How does this compare to similar libraries developers know?
  • Does it follow platform conventions (Node.js, Web APIs)?
  • Would a developer's intuition from other libraries apply here?

Review Process

Step 1: Use the API

Put yourself in a consumer's shoes:

  • What would a developer try first?
  • What questions would they have?
  • Where would they get stuck?

Step 2: Read the Types

Examine the TypeScript definitions:

  • What does autocomplete show?
  • Are overloads clear or confusing?
  • Do type errors make sense?

Step 3: Trace Common Workflows

Walk through typical tasks:

  • Opening a PDF and reading metadata
  • Modifying form fields
  • Saving changes
  • Handling errors

Step 4: Look for Friction

Identify pain points:

  • Unnecessary ceremony or boilerplate
  • Confusing parameter orders
  • Inconsistent patterns
  • Missing conveniences

Output Format

Write your review to .agents/scratch/dx-review-<scope>.md:

# DX Review: <Scope>

## Summary

Overall assessment and top priorities.

## What's Working Well

- Positive patterns to preserve

## Issues Found

### Issue 1: <Title>

**Severity:** High/Medium/Low
**Category:** Discoverability/Consistency/Ergonomics/Errors/Types/Docs

**Problem:**
Description of the issue from a developer's perspective.

**Example:**

```typescript
// Current awkward usage
```

**Recommendation:**

```typescript
// Proposed improvement
```

### Issue 2: ...

## Recommendations Summary

Prioritized list of changes to improve DX.

## Comparison Notes

How we compare to pdf-lib, pdfjs, or other libraries developers might know.

```

## Guidelines

- **Be specific** - Vague feedback isn't actionable
- **Show, don't tell** - Include code examples
- **Prioritize** - Not all issues are equal
- **Be constructive** - Propose solutions, not just problems
- **Consider tradeoffs** - Note when fixing one thing might hurt another
- **Think like a user** - You're advocating for developers who will use this

## Begin

Review the scope determined from the conversation context (or the main API if unspecified) and document your DX findings.
```

When not to use it

  • When reviewing non-public internal code
  • When performance optimization is the only goal

Limitations

  • Subjective evaluation criteria
  • Requires manual analysis

How it compares

It focuses specifically on the developer experience and ergonomics rather than just functional correctness.

Compared to similar skills

dx-review side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
dx-review (this skill)16moNo flagsIntermediate
deepwiki-rs259moReviewIntermediate
python-code-style96moReviewIntermediate
code-review-excellence195moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

deepwiki-rs

sopaco

AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.

25170

python-code-style

wshobson

Python code style, linting, formatting, naming conventions, and documentation standards. Use when writing new code, reviewing style, configuring linters, writing docstrings, or establishing project standards.

971

code-review-excellence

wshobson

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

1958

code-walk-thru

pchalasani

Use this when user wants you to walk through (code or text) files in a EDITOR to either explain how some code works, or to show the user what changes you made, etc. You would typically use this repeatedly to show the user your changes or code files one by one, sometimes with specific line-numbers. This way the user is easily able to follow along in their favorite EDITOR as you point at various files possibly at specific line numbers within those files.

670

cookbook-audit

anthropics

Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.

568

schema-markup

davila7

When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," or "breadcrumb schema." For broader SEO issues, see seo-audit.

1042

Search skills

Search the agent skills registry